Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participation

TL;DR

This paper introduces an incentive-aware federated averaging method that encourages strategic agents to participate by dynamically adjusting their data contributions, with proven performance guarantees and stable convergence.

Contribution

It proposes a novel incentive-aware FL algorithm using Nash equilibrium updates for strategic data participation, with theoretical analysis and empirical validation.

Findings

Agents achieve competitive model performance.

The scheme converges to stable participation strategies.

Performance guarantees are established for convex and nonconvex settings.

Abstract

Federated learning (FL) is a communication-efficient collaborative learning framework that enables model training across multiple agents with private local datasets. While the benefits of FL in improving global model performance are well established, individual agents may behave strategically, balancing the learning payoff against the cost of contributing their local data. Motivated by the need for FL frameworks that successfully retain participating agents, we propose an incentive-aware federated averaging method in which, at each communication round, clients transmit both their local model parameters and their updated training dataset sizes to the server. The dataset sizes are dynamically adjusted via a Nash equilibrium (NE)-seeking update rule that captures strategic data participation. We analyze the proposed method under convex and nonconvex global objective settings and establish performance guarantees for the resulting incentive-aware FL algorithm. Furthermore, under a merely monotone game setting, we consider a welfare loss minimization framework and establish asymptotic convergence of the scheme. Numerical experiments on the MNIST and CIFAR-10 datasets demonstrate that agents achieve competitive global model performance while converging to stable data participation strategies.